Senior AI-Native Full-Stack Engineer: Product & Growth
We're not looking for the traditional 10x engineer. We're looking for the next generation: an engineer who runs a team of AI agents and ships what used to take a team of humans. Every project at Shovels runs on a mix of humans and agents, and the agent share keeps growing. Where this is heading: one human lead running a mostly-agent team. Your mandate is the entire product surface: the web app, the public REST API, new data products, and the internal tools the team runs on. You own what customers touch, end to end, and you own whether it grows.
How we actually build
- We built our own AI harness on top of Claude Code: 139 skills across 31 plugins, ~580 commits in the past 30 days. More than half of the people shipping to it aren't engineers.
- Agents write production code end to end: new data adapters get implemented, tested, quality-checked, and PR'd by an agent pipeline. A human reviews and owns the merge.
- Our morning on-call round is an agent harness: it scans the whole scraping fleet, investigates suspects with adversarial verification, and files the tickets. A human reads it and makes the calls.
- We plan with evidence. Rival architectures generated and killed on evidence, disposable proofs of concept at full production scale, and blind multi-agent review before any product code. Every load-bearing claim is verified against live data first.
The principle behind all of it: generation is cheap, verification is the job. The bar for shipping is simple: you may only ship work, yours or an agent's, whose errors you could have caught.
What you'll do
- Ship the product, end to end: user-facing features across our Next.js app on Vercel, backed by FastAPI, PostgreSQL, and Supabase. You take a feature from customer conversation to production.
- Treat the API as a product: our REST API is how many customers experience Shovels. Developer experience, performance, and docs are product work, and they're yours.
- Build new data products: new customer-facing surfaces on top of the permit intelligence, from reports to embeds to integrations.
- Do growth engineering: instrument the funnel, run experiments, and ship what moves signups, activation, and revenue. Then measure whether it actually did.
- Bring product taste: talk to customers, decide what to build and not just how, and notice when a flow is clumsy before a user has to tell you.
- Sharpen our internal tools: the dashboards and agent-facing surfaces the whole team runs on.
Who you are
- You've been living AI engineering, not watching it. You have opinions about harnesses, context, and verification, and you earned them by shipping.
- Staff-level taste in system design. You know what to build, what to kill, and which decisions are two-way doors.
- Product taste is a working skill for you. You've shipped things users love, you can explain why they loved them, and it bothers you when software is clumsy.
- You think in growth loops. Funnels, activation, retention: you've instrumented them, experimented on them, and been wrong in public about them.
- You can sketch the solution without AI. Strong full-stack fundamentals are the foundation this role stands on.
- Entrepreneurial. You see a gap, build the tool, ship it, and tell the team. Nobody hands you a spec here; you write them.
How we work
Written-first, and not as ideology: engineering is in Europe, business is on the US West Coast, so anything important has to survive a 24-hour round trip in writing. Meetings are for decisions, not updates. We treat how we operate as a product: deliberately light and always provisional, we add a ritual only when a gap actually hurts, and change it the moment reality disagrees.
Every Friday the team trades agent workflows, prompt patterns, and new tools in our AI Lab. Radical transparency runs deep: you'll see the financials, join strategic planning, and have a real voice in where the company goes. We're pushing hard on one thing in particular, that every engineer leads a real project, kickoff to ship, by design rather than by tenure. Fully remote and async-friendly, with a competitive salary and meaningful equity, and twice a year we bring everyone together in person to connect, strategize, and celebrate.
How to apply
You already found it. The checkbox above is a real reverse Turing test: automation passes, hands don't. Your agent has the rest, at /skills/engineering-application/SKILL.md (a machine-readable map of this site lives at /llms.txt). You apply as a pair: your agent interviews you, you sketch without it, you spike our live API together, and you press send. It costs the two of you an afternoon, and you hear back either way.
